检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Boosting polyp screening with improved point-teacher weakly semi-supervised

引用

computers in Biology and Medicine 2025年 191卷 109998-109998页

作者： Du, Xiuquan Zhang, Xuejun Chen, Jiajia Li, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China Department of Neurology Shuyang Affiliated Hospital of Nanjing University of Traditional Chinese Medicine Suqian China School of Computer Science and Technology Anhui University Hefei China

Polyps, like a silent time bomb in the gut, are always lurking and can explode into deadly colorectal cancer at any time. Many methods are attempted to maximize the early detection of colon polyps by screening, however, there are still face some challenges: (i) the scarcity of per-pixel annotation data and clinical features such as the blurred boundary and low contrast of polyps result in poor performance. (ii) existing weakly semi-supervised methods directly using pseudo-labels to supervise student tend to ignore the value brought by intermediate features in the teacher. To adapt the point-prompt teacher model to the challenging scenarios of complex medical images and limited annotation data, we creatively leverage the diverse inductive biases of CNN and Transformer to extract robust and complementary representation of polyp features (boundary and context). At the same time, a novel designed teacher–student intermediate feature distillation method is introduced rather than just using pseudo-labels to guide student learning. Comprehensive experiments demonstrate that our proposed method effectively handles scenarios with limited annotations and exhibits good segmentation performance. All code is available at https://***/dxqllp/WSS-Polyp. © 2025 Elsevier Ltd

关键词： Weakly semi-supervised Medical image segmentation Boundary extraction Feature distillation

来源：评论

学校读者我要写书评

暂无评论

Black⁃box adversarial attacks with imperceptible fake user profiles for recommender systems

引用

南京大学学报(自然科学版) 2024年第6期60卷 881-899页

作者： Qian Fulan Liu Jinggang Chen Hai Chen Wenbin Zhao Shu Zhang Yanping Artificial Intelligence Institute Anhui UniversityHefei230601China Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityHefei230601China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui UniversityHefei230601China

Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation *** is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack ***,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial *** reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial *** address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler ***,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial *** uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial *** results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.

关键词： recommendation systems adversarial examples transferability imperceptible

来源：评论

学校读者我要写书评

暂无评论

RankDNN: Learning to Rank for Few-Shot Learning 37

RankDNN: Learning to Rank for Few-Shot Learning

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Guo, Qianyu Haotong, Gong Wei, Xujun Fu, Yanwei Yu, Yizhou Zhang, Wenqiang Ge, Weifeng Nebula AI Group School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Academy for Engineering & Technology Fudan University Shanghai China Department of Computer Science The University of Hong Kong Hong Kong

ISBN: (纸本)9781577358800

This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on few-shot learning and is complementary to state-of-the-art methods. The core component of our deep neural network is a simple MLP, which takes as input an image triplet encoded as the difference between two vector-Kronecker products, and outputs a binary relevance ranking order. The proposed RankMLP can be built on top of any state-of-the-art feature extractors, and our entire deep neural network is called the ranking deep neural network, or RankDNN. Meanwhile, RankDNN can be flexibly fused with other post-processing methods. During the meta test, RankDNN ranks support images according to their similarity with the query samples, and each query sample is assigned the class label of its nearest neighbor. Experiments demonstrate that RankDNN can effectively improve the performance of its baselines based on a variety of backbones and it outperforms previous state-of-the-art algorithms on multiple few-shot learning benchmarks, including miniImageNet, tieredImageNet, Caltech-UCSD Birds, and CIFAR-FS. Furthermore, experiments on the cross-domain challenge demonstrate the superior transferability of *** code is available at: https://***/guoqianyu-alberta/RankDNN. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Generation Method Based on Probability Histogram Equalization

Adversarial Example Generation Method Based on Probability H...

引用

Chinese Control Conference (CCC)

作者： Youqing Fang Jingwen Jia Yuhai Yang Wan-Li Lyu Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China

CNNs (Convolutional Neural Networks) have a good performance on most classification tasks, but they are vulnerable when meeting adversarial examples. Research and design of highly aggressive adversarial examples can help enhance the security and robustness of CNNs. The transferability of adversarial examples is still low in black-box settings. Therefore, an adversarial example method based on probability histogram equalization, namely HE-MI-FGSM (Histogram Equalization Momentum Iterative Fast Gradient Sign Method) is proposed. In each iteration of the adversarial example generation process, the original input image is randomly histogram equalized, and then the gradient is calculated to generate adversarial perturbations to mitigate overfitting in the adversarial example. The effectiveness of the method is verified on the ImageNet dataset. Compared with the advanced method I-FGSM (Iterative Fast Gradient Sign Method) and MI-FGSM (Momentum I-FGSM), the attack success rate in the adversarial training network increased by 27.9% and 7.7% on average, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient polar coding scheme and implementation with shared information bits

引用

Science China(Information Sciences) 2022年第10期65卷 309-310页

作者： Wenyue ZHOU Xiaofeng ZHOU Yifei SHEN Qiang LIU Liping LI Chuan ZHANG Laboratory of Efficient Architectures for Digital-communication and Signal-processing (LEADS) National Mobile Communications Research Laboratory Southeast University Purple Mountain Laboratories Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education of China Anhui University

Dear editor,Polar codes invented by Ar?kan [1] can achieve the capacity of symmetric binary-input discrete memoryless channels(B-DMCs) with an infinite code length. However, it suffers from unsatisfactory performance with a finite code length [2]. The performance degradation of polar codes with a finite code length is caused by the inadequate polarization phenomenon;

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monotonic and nonmonotonic gentzen deduction systems for L_(3)-valued propositional logic

引用

Frontiers of computer Science 2021年第3期15卷 123-135页

作者： Cungen CAO Lanxi HU Yuefei SUI Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China

A sequent is a pair(Г,△),which is true under an as-signment if either some formula inГis false,or some formula in △ is *** L3-valued propositional logic,a mulisequent is a triple △|Θ|Г,which is true under an assignment if either some formula in △ has truth-value t,or some formula in Θ has truth-value m,or some formula in Г has truth-value￡.Corre-spondingly there is a sound and complete Gentzen deduction system G for multisequents which is ***,a CO-multisequent is a triple △:Θ:Г,which is valid if there is an assignment v in which each formula in△has truth-value≠t,each formula in Θ has truth-value≠m,and each formula in Г has truth-value≠￡.Correspondingly there is a sound and com-plete Gentzen deduction system G-for co-multisequents which is nonmonotonic.

关键词： three-valued logic multisequent co-multise-quent monotonicity Gentzen deduction system

来源：评论

学校读者我要写书评

暂无评论

A Circularly Polarized Antenna for GPS L1 band with U-Shaped-Like Strips

A Circularly Polarized Antenna for GPS L1 band with U-Shaped...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Meng, Lulu Huang, Zhixiang Li, Yingsong Anhui University School of Electronic and Information Engineering Hefei230601 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9781665452366

A U-shaped-like parasitic strip loading antenna is proposed and designed, which can work in L1 band of GPS with circular polarization (CP) characteristics. The antenna consists of ground plane, dielectric, radiation patch and U-shaped-like parasitic strips using a simple coaxial feed probe. The asymmetric U-shaped-like strips are to realize CP. The simulation and optimization results for the modeled directional CP antenna show that the axial ratio bandwidth is 10MHz and the impedance bandwidth is 30MHz, which can meet the requirements for GPS L1 band. © 2022 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

A Faster Parameterized Algorithm for Bipartite 1-Sided Vertex Explosion 16th

A Faster Parameterized Algorithm for Bipartite 1-Sided Vert...

引用

16th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2023

作者： Liu, Yunlong Xiao, Guang Liu, Ao Wu, Di Huang, Jingui College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China Xiangtan University Xiangtan411101 China School of Computer Science and Engineering Central South University Changsha410083 China

ISBN: (纸本)9783031496134

Given a bipartite graph G = (T∪ B, E), the problem bipartite 1-sided vertex explosion is to decide whether there exists a planar 2-layer embedding of G after exploding at most k vertices of B. For this problem, which is known to be NP-complete, parameterized algorithms have received increasing attention more recently. In this paper, we focus on the problem parameterized by the number k of allowed exploded vertices of B and develop a faster algorithm for it. More specifically, we show that this parameterized problem admits a kernel of at most 10.5k vertices, and present a fixed-parameter tractable algorithm running in time O(2. 31 k· m), where m is the number of edges of G. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Virtual Machine Migration Algorithm in Data Centers 3

Energy-Efficient Virtual Machine Migration Algorithm in Data...

引用

3rd International conference on computer, Big Data and Artificial Intelligence, ICCBDAI 2022

作者： Wu, Xiaodong Zeng, Taisheng School of Mathmatics and Computer Science Quanzhou Normal University Fujian Province Quanzhou362000 China Fujian Provincial Key Laboratory of Intensive Computing Fujian Province Quanzhou362000 China Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Province Quanzhou362000 China

The issue of data center power consumption is becoming increasingly serious. One of the most effective techniques for increasing resource utilization and lowering power consumption is virtual machine consolidation. This paper proposes a threshold-based energy-efficient and SLA-aware algorithm for virtual machine migration and consolidation. Based on statistics and analysis of historical virtual machine status, the algorithm dynamically obtains the upper CPU utilization threshold of the physical servers and identifies whether to perform the virtual machine migration, so as to reduce the number of active hosts to save energy. The experimental results demonstrate that the proposed algorithm has better comprehensive performance. When compared to the existing algorithm, our method can effectively decrease energy consumption and SLA violations. © Published under licence by IOP Publishing Ltd.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：